Animal acoustic identification, denoising, and source separation using generative adversarial networks

Soundscapes contain rich ecological information, offering insights into both biodiversity and ecosystem dynamics. However, the sheer volume of data produced by passive acoustic monitoring presents significant challenges for scalable analysis and ecological interpretation. While convolutional neural networks (CNNs) have advanced species classification in bioacoustics, they often struggle with identifying acoustic targets in acoustic space and quantifying soundscapes’ characteristics.
In this study, we propose a novel spectrogram-to-spectrogram translation framework based on generative adversarial networks (GANs) to isolate and quantify acoustic sources within soundscape recordings. Our method is trained on paired spectrogram images: original full-spectrogram representations and target spectrogram representations containing only the vocalizations of specific sound labels. This design enables the model to learn source-specific mappings and perform both the species and community-level separ..., , # Animal acoustic identification, denoising, and source separation using generative adversarial networks

Dataset DOI: [10.5061/dryad.vhhmgqp6k](10.5061/dryad.vhhmgqp6k)

## Description

This compressed archive (Spectrogram_GAN.zip) contains code, data, and analysis outputs related to the manuscript \"Animal Acoustic Identification, Denoising, and Source Separation Using Generative Adversarial Networks\". It includes scripts for transforming audio into spectrograms, preparing training pairs, and training/testing generative models for spectrogram reconstruction. The materials support both species-level and community-level acoustic analysis and quantitative evaluations.

### Data and File Structure

The repository contains the compressed package Spectrogram_GAN.zip, which includes the following files and directories:

**Python Scripts**

job01_wav_to_spec.py: It performs Fourier transform on audio files and generates corresponding spectrograms.

Input: wav01.wav → Output: spec01.png

job02_...,